By Topic

Performance analysis of parallel computing in a distributed overlay network

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Jay W. Y. Lim ; Faculty of Information Technology, Multimedia University, Cyberjaya, 63100, Malaysia ; Poo Kuan Hoong ; Eng-Thiam Yeoh ; Ian K. T. Tan

There are many data and computation intensive applications that generally require very high performance and a lot of computing resources which lead to the increase in the overall execution time. Parallel computing can improve overall execution time which involves breaking up large program into smaller pieces that can be executing in multi processors system. While, distributed computing offers some advantages for parallel computing, where multiple connected processors can run in parallel by contributing their computing time and memory storage. However, due to the nature of heterogeneity of processing power in distributed computing, the effect of imbalance of workload distribution between processors is an important factor to be taken into consideration. In this paper, we conducted simulations of Pi value computation for tree-based distributed system under several of types of workloads distributions. We measured the overall execution time to study and analyze the effect of different workloads distribution. From our simulation results, we found that the increment of waiting time for a processor to receive back a result significantly impact the overall execution time as well as the scalability of the distributed system.

Published in:

TENCON 2011 - 2011 IEEE Region 10 Conference

Date of Conference:

21-24 Nov. 2011